alt Hacker NewsShow HN: Agent Passport – OAuth-like identity verification for AI agents
Hi HN,
I built Agent Passport, an open-source identity verification layer for AI agents. Think "Sign in with Google, but for Agents."
The problem: AI agents are everywhere now (OpenClaw has 180K+ GitHub stars, Moltbook had 2.3M agent accounts), but there's no standard way for agents to prove their identity. Malicious agents can impersonate others, and skill/plugin marketplaces have no auth layer. Cisco's security team already found data exfiltration in third-party agent skills.
Agent Passport solves this with: - Ed25519 challenge-response authentication (private keys never leave the agent) - JWT identity tokens (60-min TTL, revocable) - Risk engine that scores agents 0-100 (allow/throttle/block) - One-line verification for apps: `const result = await passport.verify(token)`
It's fully open source (MIT), runs on free tiers ($0/month), and has a published npm SDK.
GitHub: https://github.com/zerobase-labs/agent-passport Docs: https://github.com/zerobase-labs/agent-passport/blob/main/do... Live demo: https://agent-passport.vercel.app
Built this because I kept seeing the same security gap in every agent platform. Happy to answer questions about the architecture or the agent identity problem in general.
Comments
SPIFFE/SPIRE could work for the identity layer. The risk engine concept is cool. Would love to see that applied to machine identities that are working "on-behalf-of" humans.
Very cool. Reminds me a lot of EIP-8004 https://eips.ethereum.org/EIPS/eip-8004
Interesting approach. The risk scoring (0-100) is the part I find most promising. Identity alone isn't enough — you need dynamic trust assessment.
One thing I'd add: agent identity becomes much more complex in multi-agent systems where agents coordinate with each other, not just with services. In that scenario, you need agents to verify each other's identity AND authority (is this agent authorized to claim this task? edit this file? send this message?). The OAuth model handles service-to-agent auth well but doesn't address agent-to-agent trust.
SPIFFE/SPIRE suggestion above is good for infrastructure-level identity. But for application-level trust between cooperating agents, you might want something more like a capability-based system where agents can delegate specific permissions to each other without a central authority.